Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

librarian

bởi nonlinear

Search & Research
326Lượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Conversational interface for semantic book search (companion skill for Librarian project)

Mô tả

Kỹ năng này làm gì

A conversational interface for searching a personal book library using semantic embeddings. Ask questions in natural language and get back synthesized answers with page-level citations. Runs as a companion to the Librarian project via a three-layer architecture: AI skill, shell wrapper, and Python search engine.

Returns precise citations with page and paragraph numbers from local files instead of summarizing from memory or requiring a web search.

Khi nào nên dùng

  • Finding what a specific author says about a topic across your library
  • Locating passages in a single book by concept or keyword
  • Getting cited answers from a topic folder of books
  • Cross-referencing ideas across multiple texts without opening each file
  • Querying a personal research archive by natural language

Quy trình ví dụ

ĐẦU VÀO

User asks: What does Graeber say about the origins of money?

AGENT
  1. 1

    Load .library-index.json and .topic-index.json metadata

  2. 2

    Match query against known book titles and topic IDs to infer scope

  3. 3

    Build shell command: ./librarian.sh "origins of money" topic finance 5

  4. 4

    Parse JSON results from Python search engine

  5. 5

    Synthesize answer and format citations with page numbers

ĐẦU RA

Paragraph summarizing Graeber's argument with inline citations like [Debt: The First 5000 Years, p.21, ¶2] and a sources list

Yêu cầu

  • Librarian parent project installed (github.com/nonlinear/librarian)

Cài đặt

clawhub install nonlinear/librarian

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết